ICLR

Is conditional generative modeling all you need for decision-making?

Sampling with Mollified Interaction Energy Descent

Learning Proximal Operators to Discover Multiple Optima

AnyDA: Anytime Domain Adaptation

Label-free Concept Bottleneck Models

Learning to Grow Pretrained Models for Efficient Transformer Training

PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning

FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation

Contrastive Audio-Visual Masked Autoencoder

ISAAC Newton: Input-based Approximate Curvature for Newton’s Method

SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments

DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics

Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness

What Is Missing in IRM Training and Evaluation? Challenges and Solutions

Hyper-Decision Transformer for Efficient Online Policy Adaptation

TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks

A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity

Understanding new tasks through the lens of training data via exponential tilting

Planning with Large Language Models for Code Generation

Temperature Schedules for self-supervised contrastive methods on long-tail data

Adversarial Support Alignment

Data-Efficient Graph Grammar Learning for Molecular Generation

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

Can an Image Classifier Suffice For Action Recognition?

RegionViT: Regional-to-Local Attention for Vision Transformers

AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning

Bi-linear Value Networks for Multi-goal Reinforcement Learning

Overcoming The Spectral Bias of Neural Value Approximation

Neural Parameter Allocation Search

Extending the WILDS Benchmark for Unsupervised Adaptation

Network Augmentation for Tiny Deep Learning

Multi-Critic Actor Learning: Teaching RL Policies to Act with Style

ComPhy: Compositional Physical Reasoning of Objects and Events from Videos

How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis

Optimizer Amalgamation

How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective

RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation

Topological Experience Replay

Linking Emergent and Natural Languages via Corpus Transfer

Monotonic Differentiable Sorting Networks

Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

Controlling Directions Orthogonal to a Classifier

DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools

Natural Language Descriptions of Deep Visual Features

Reverse Engineering of Imperceptible Adversarial Image Perturbations

FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations

Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach

Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning

AdaFuse: Adaptive Temporal Fusion Network for Efficient Action Recognition

VA-RED^2: Video Adaptive Redundancy Reduction

Nano-Material Configuration Design with Deep Surrogate Langevin Dynamics

Lite Transformer with Long-Short Range Attention

Robust Overfitting may be mitigated by properly learned smoothening

On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning

Generating Adversarial Computer Programs using Optimized Obfuscations

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Grounding Physical Concepts of Objects and Events Through Dynamic Visual Reasoning

Learning Task Decomposition with Ordered Memory Policy Network

SenSeI: Sensitive Set Invariance for Enforcing Individual Fairness

Individually Fair Gradient Boosting

Individually Fair Ranking

Statistical inference for individual fairness

Learning-based Support Estimation In Sublinear Time

Large Associative Memory Problem in Neurobiology and Machine Learning

Can a Fruit Fly Learn Word Embeddings?

Sign-OPT: Defending the hard-label black-box cyber attack

SenSR: the first practical algorithm for individual fairness

Why Gradient Clipping accelerates training for neural networks

CLEVRER: The first video dataset for neuro-symbolic reasoning

Fast and efficient black-box testing for AI cybersecurity

Learning to learn with distributional signatures for text data

Layer-wise federated learning with FedMA

Learning Rate Rewinding for elegant neural network pruning

Generative Ratio Matching Networks

Implementation Matters in Deep RL: A Case Study on PPO and TRPO

Once for All: Train One Network and Specialize it for Efficient Deployment

Deep Audio Priors Emerge From Harmonic Convolutional Networks

A Closer Look at Deep Policy Gradients